GRACEメールマガジン2012/5/8 第20号

◆□◆GRACEメールマガジン2012/5/8 第20号◆□◆



■日 程:
■会 場:場所:国立情報学研究所(NII)
20階 ミーティングルーム1・2(2009・2010)
〒101-8430 東京都千代田区一ツ橋2-1-2
■主催: NII 先端ソフトウェア工学国際研究センター(GRACEセンター)
■概 要:
今回のGRACEセミナーはアリゾナ州立大学の Chitta Baral 先生に
知識表現言語である解集合プログラミング (Answer Set Programming)



< Chitta Baral 先生の発表概要とご紹介>
Title: Lessons from Efforts to Automatically Translate English to
Knowledge Representation Languages

Our long term goal is to develop systems that can “understand” natural
language text. By “understand” we mean that the system can take
natural language text as input and answer questions with respect to
that text. A key component in building such systems is to be able to
translate natural language text into appropriate knowledge
representation (KR) languages. Our approach to achieve that is
inspired by Montague’s path breaking thesis (1970) of viewing English
as a formal language and by the research in natural language
semantics. Our approach is based on PCCG (Probabilistic Combinatorial
Categorial Grammars), lambda-calculus and statistical learning of
parameters. In an initial work, we start with an initial vocabulary
consisting of lambda-calculus representations of a small set of words
and a training corpus of sentences and their representation in a KR
language. We develop a learning based system that learns the
lambda-calculus representation of words from this corpus and
generalizes it to words of the same category. The key and novel
aspect in this learning is the development of Inverse Lambda
algorithms which when given lambda-expressions beta and gamma can come
up with an alpha such that application of alpha to beta (or beta to
alpha) will give us gamma. We augment this with learning of weights
associated with multiple meanings of words. Our current system
produces improved results on standard corpora on natural language
interfaces for robot command and control and database queries. In a
follow-up work we are able to use patterns to make guesses regarding
the initial vocabulary. This together with learning of parameters
allow us to develop a fully automated (without any initial vocabulary)
way to translate English to designated KR languages. In an on-going
work we use Answer Set Programming as the target KR language and focus
on (a) solving combinatorial puzzles that are described in English and
(b) answering questions with respect to a chapter in a ninth grade
biology book. The systems that we are building are good examples of
integration of results from multiple sub-fields of AI and computer
science, viz.: machine learning, knowledge representation, natural
language processing, lambda-calculus (functional programming) and
ontologies. In this presentation we will describe our approach and our
system and elaborate on some of the lessons that we have learned from
this effort.

Chitta Baral received his PhD degree in Computer Science in 1991 from
University of Maryland, College Park, USA. From 1991 to 1999, he was
an Assistant Professor at University of Texas at El Paso. From 1999
to 2002, he was an Associate Professor at Arizona State University;
and since 2002 he is a Professor at Arizona State University. His
main areas of research interests are Artificial Intelligence,
Knowledge Representation and Reasoning, Declarative programming,
Answer set programming, Bioinformatics, Autonomous agents, Logic
Programming, Cognitive Robotics, Reasoning about actions, Temporal
logic based specification languages.

●GRACEメールマガジンの 第20号をお届けしました。


カテゴリー: メルマガ パーマリンク